76aa370f44
Due to recently reported problems with having the inlining threshold multiplier set fairly high (x3), this patch removes the multiplier while addressing the regressions seen by doing so in adjustInliningThreshold(). The specific cases that benefit from inlining that were now found to be in need of handling contain a considerable number of memory accesses to the same memory in both caller and callee.
138 lines
6.0 KiB
C++
138 lines
6.0 KiB
C++
//===-- SystemZTargetTransformInfo.h - SystemZ-specific TTI ---------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_SYSTEMZ_SYSTEMZTARGETTRANSFORMINFO_H
|
|
#define LLVM_LIB_TARGET_SYSTEMZ_SYSTEMZTARGETTRANSFORMINFO_H
|
|
|
|
#include "SystemZTargetMachine.h"
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
#include "llvm/CodeGen/BasicTTIImpl.h"
|
|
|
|
namespace llvm {
|
|
|
|
class SystemZTTIImpl : public BasicTTIImplBase<SystemZTTIImpl> {
|
|
typedef BasicTTIImplBase<SystemZTTIImpl> BaseT;
|
|
typedef TargetTransformInfo TTI;
|
|
friend BaseT;
|
|
|
|
const SystemZSubtarget *ST;
|
|
const SystemZTargetLowering *TLI;
|
|
|
|
const SystemZSubtarget *getST() const { return ST; }
|
|
const SystemZTargetLowering *getTLI() const { return TLI; }
|
|
|
|
unsigned const LIBCALL_COST = 30;
|
|
|
|
bool isInt128InVR(Type *Ty) { return Ty->isIntegerTy(128) && ST->hasVector(); }
|
|
|
|
public:
|
|
explicit SystemZTTIImpl(const SystemZTargetMachine *TM, const Function &F)
|
|
: BaseT(TM, F.getDataLayout()), ST(TM->getSubtargetImpl(F)),
|
|
TLI(ST->getTargetLowering()) {}
|
|
|
|
/// \name Scalar TTI Implementations
|
|
/// @{
|
|
|
|
unsigned adjustInliningThreshold(const CallBase *CB) const;
|
|
|
|
InstructionCost getIntImmCost(const APInt &Imm, Type *Ty,
|
|
TTI::TargetCostKind CostKind);
|
|
|
|
InstructionCost getIntImmCostInst(unsigned Opcode, unsigned Idx,
|
|
const APInt &Imm, Type *Ty,
|
|
TTI::TargetCostKind CostKind,
|
|
Instruction *Inst = nullptr);
|
|
InstructionCost getIntImmCostIntrin(Intrinsic::ID IID, unsigned Idx,
|
|
const APInt &Imm, Type *Ty,
|
|
TTI::TargetCostKind CostKind);
|
|
|
|
TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);
|
|
|
|
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
|
|
TTI::UnrollingPreferences &UP,
|
|
OptimizationRemarkEmitter *ORE);
|
|
|
|
void getPeelingPreferences(Loop *L, ScalarEvolution &SE,
|
|
TTI::PeelingPreferences &PP);
|
|
|
|
bool isLSRCostLess(const TargetTransformInfo::LSRCost &C1,
|
|
const TargetTransformInfo::LSRCost &C2);
|
|
/// @}
|
|
|
|
/// \name Vector TTI Implementations
|
|
/// @{
|
|
|
|
unsigned getNumberOfRegisters(unsigned ClassID) const;
|
|
TypeSize getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const;
|
|
|
|
unsigned getCacheLineSize() const override { return 256; }
|
|
unsigned getPrefetchDistance() const override { return 4500; }
|
|
unsigned getMinPrefetchStride(unsigned NumMemAccesses,
|
|
unsigned NumStridedMemAccesses,
|
|
unsigned NumPrefetches,
|
|
bool HasCall) const override;
|
|
bool enableWritePrefetching() const override { return true; }
|
|
|
|
bool hasDivRemOp(Type *DataType, bool IsSigned);
|
|
bool prefersVectorizedAddressing() { return false; }
|
|
bool LSRWithInstrQueries() { return true; }
|
|
bool supportsEfficientVectorElementLoadStore() { return true; }
|
|
bool enableInterleavedAccessVectorization() { return true; }
|
|
|
|
InstructionCost getArithmeticInstrCost(
|
|
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
|
|
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
ArrayRef<const Value *> Args = {}, const Instruction *CxtI = nullptr);
|
|
InstructionCost getShuffleCost(TTI::ShuffleKind Kind, VectorType *Tp,
|
|
ArrayRef<int> Mask,
|
|
TTI::TargetCostKind CostKind, int Index,
|
|
VectorType *SubTp,
|
|
ArrayRef<const Value *> Args = {},
|
|
const Instruction *CxtI = nullptr);
|
|
unsigned getVectorTruncCost(Type *SrcTy, Type *DstTy);
|
|
unsigned getVectorBitmaskConversionCost(Type *SrcTy, Type *DstTy);
|
|
unsigned getBoolVecToIntConversionCost(unsigned Opcode, Type *Dst,
|
|
const Instruction *I);
|
|
InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
|
|
TTI::CastContextHint CCH,
|
|
TTI::TargetCostKind CostKind,
|
|
const Instruction *I = nullptr);
|
|
InstructionCost getCmpSelInstrCost(
|
|
unsigned Opcode, Type *ValTy, Type *CondTy, CmpInst::Predicate VecPred,
|
|
TTI::TargetCostKind CostKind,
|
|
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
const Instruction *I = nullptr);
|
|
using BaseT::getVectorInstrCost;
|
|
InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
|
|
TTI::TargetCostKind CostKind,
|
|
unsigned Index, Value *Op0, Value *Op1);
|
|
bool isFoldableLoad(const LoadInst *Ld, const Instruction *&FoldedValue);
|
|
InstructionCost
|
|
getMemoryOpCost(unsigned Opcode, Type *Src, MaybeAlign Alignment,
|
|
unsigned AddressSpace, TTI::TargetCostKind CostKind,
|
|
TTI::OperandValueInfo OpInfo = {TTI::OK_AnyValue, TTI::OP_None},
|
|
const Instruction *I = nullptr);
|
|
|
|
InstructionCost getInterleavedMemoryOpCost(
|
|
unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
|
|
Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
|
|
bool UseMaskForCond = false, bool UseMaskForGaps = false);
|
|
|
|
InstructionCost getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
|
|
TTI::TargetCostKind CostKind);
|
|
|
|
bool shouldExpandReduction(const IntrinsicInst *II) const;
|
|
/// @}
|
|
};
|
|
|
|
} // end namespace llvm
|
|
|
|
#endif
|